Profiles2023-2026
Jing Yao
Microsoft Research Asia
10Papers
0Last author
23Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers10
- AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value DifferenceAuthor 1 of 9ICLR 2026 · 4 citations
- MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual QuestionsAuthor 8 of 10AAAI 2026 · 2 citations
- Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value CodebookAuthor 3 of 7ICML 2026 · 1 citation
- IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective OptimizationAuthor 4 of 10AAAI 2026 · 1 citation
- Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMsAuthor 2 of 8ICML 2026
- Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language ModelsAuthor 2 of 5NeurIPS 2025 · 6 citations
- Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and EnhancementAuthor 2 of 6ACL 2025 · 3 citations
- Unintended Harms of Value-Aligned LLMs: Psychological and Empirical InsightsAuthor 4 of 6ACL 2025
- RecExplainer: Aligning Large Language Models for Explaining Recommendation ModelsAuthor 2 of 4KDD 2024 · 18 citations
- Towards Explainable Collaborative Filtering with Taste Clusters LearningAuthor 3 of 8WWW 2023 · 10 citations
